Detection of RFID cloning attacks: A spatiotemporal trajectory data stream-based practical approach

Abstract

With the rapid development of the internet of things (IoT), radio frequency identification (RFID) technology plays an important role in various fields. However, tags are vulnerable to cloning attacks because they are limited by size and production costs. A cloning attack fabricates one or more replicas of a genuine tag, which behave exactly the same as the genuine tag and can deceive the reader to obtain legitimate authorization, leading to potential economic loss or reputation damage. Many advanced solutions have been proposed to combat cloning attacks. Existing trajectory-based RFID clone detection methods use historical trajectories for model training. However, the environment of the RFID monitoring area is complex and diverse and changes in real time. The features trained based on historical trajectories cannot effectively adapt to the complex environment. In this article, we make a novel attempt to counterattack tag cloning based on real-time trajectories. We propose the clone attack detection approach (deClone), which can intuitively and accurately display the positions of abnormal tags in real time. It requires only commercial off-the-shelf (COTS) RFID devices, unlike methods based on radio frequency (RF) fingerprints and synchronization keys, which require additional hardware devices or software redesign. According to the experimental results, our scheme improves the detection precision by 16.71% compared with that of the existing trajectory-based detection methods.